Skip to content

Remove archive after it is extracted to save disk space #1351

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
PGijsbers merged 5 commits into from
Sep 29, 2024
Merged

Remove archive after it is extracted to save disk space #1351

Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
f490d66
Remove archive after it is extracted to save disk space
PGijsbers Sep 13, 2024
a7defec
Leave a marker after removing archive to avoid redownload
PGijsbers Sep 28, 2024
6be724e
Automatic refresh if expected marker is absent
PGijsbers Sep 28, 2024
8f78f0c
Be consistent about syntax use for path construction
PGijsbers Sep 28, 2024
731b3e1
Merge branch 'develop' into add/cleanup
PGijsbers Sep 28, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Leave a marker after removing archive to avoid redownload
  • Loading branch information
@PGijsbers
PGijsbers committed Sep 28, 2024
commit a7defec25c93af73c280fc2fdd584342b1075b59
30 changes: 20 additions & 10 deletions openml/_api_calls.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
# License: BSD 3-Clause
from __future__ import annotations

import contextlib
import hashlib
import logging
import math
Expand Down Expand Up @@ -172,7 +173,6 @@ def _download_minio_file(
if destination.is_file() and destination.suffix == ".zip":
with zipfile.ZipFile(destination, "r") as zip_ref:
zip_ref.extractall(destination.parent)
destination.unlink()

except minio.error.S3Error as e:
if e.message is not None and e.message.startswith("Object does not exist"):
Expand All @@ -185,14 +185,14 @@ def _download_minio_file(
def _download_minio_bucket(source: str, destination: str | Path) -> None:
"""Download file ``source`` from a MinIO Bucket and store it at ``destination``.

Does not redownload files which already exist.

Parameters
----------
source : str
URL to a MinIO bucket.
destination : str | Path
Path to a directory to store the bucket content in.
exists_ok : bool, optional (default=True)
If False, raise FileExists if a file already exists in ``destination``.
"""
destination = Path(destination)
parsed_url = urllib.parse.urlparse(source)
Expand All @@ -205,13 +205,23 @@ def _download_minio_bucket(source: str, destination: str | Path) -> None:

for file_object in client.list_objects(bucket, prefix=prefix, recursive=True):
if file_object.object_name is None:
raise ValueError("Object name is None.")

_download_minio_file(
source=source.rsplit("/", 1)[0] + "/" + file_object.object_name.rsplit("/", 1)[1],
destination=Path(destination, file_object.object_name.rsplit("/", 1)[1]),
exists_ok=True,
)
raise ValueError(f"Object name is None for object {file_object!r}")

marker = Path(destination, file_object.etag)
if marker.exists():
continue

file_destination = Path(destination, file_object.object_name.rsplit("/", 1)[1])
with contextlib.suppress(FileExistsError):
_download_minio_file(
source=source.rsplit("/", 1)[0] + "/" + file_object.object_name.rsplit("/", 1)[1],
destination=file_destination,
exists_ok=False,
)

if file_destination.is_file() and file_destination.suffix == ".zip":
file_destination.unlink()
marker.touch()


def _download_text_file(
Expand Down